1 files changed, 65 insertions, 113 deletions

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index bd28f386bd0..6f9de61dce5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -73,12 +73,7 @@ static void __tunnel_dst_set(struct ip_tunnel_dst *idst,
 {
 	struct dst_entry *old_dst;
 
-	if (dst) {
-		if (dst->flags & DST_NOCACHE)
-			dst = NULL;
-		else
-			dst_clone(dst);
-	}
+	dst_clone(dst);
 	old_dst = xchg((__force struct dst_entry **)&idst->dst, dst);
 	dst_release(old_dst);
 }
@@ -93,83 +88,33 @@ static void tunnel_dst_reset(struct ip_tunnel *t)
 	tunnel_dst_set(t, NULL);
 }
 
-static void tunnel_dst_reset_all(struct ip_tunnel *t)
+void ip_tunnel_dst_reset_all(struct ip_tunnel *t)
 {
 	int i;
 
 	for_each_possible_cpu(i)
 		__tunnel_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
 }
+EXPORT_SYMBOL(ip_tunnel_dst_reset_all);
 
-static struct dst_entry *tunnel_dst_get(struct ip_tunnel *t)
+static struct rtable *tunnel_rtable_get(struct ip_tunnel *t, u32 cookie)
 {
 	struct dst_entry *dst;
 
 	rcu_read_lock();
 	dst = rcu_dereference(this_cpu_ptr(t->dst_cache)->dst);
-	if (dst)
-		dst_hold(dst);
-	rcu_read_unlock();
-	return dst;
-}
-
-static struct dst_entry *tunnel_dst_check(struct ip_tunnel *t, u32 cookie)
-{
-	struct dst_entry *dst = tunnel_dst_get(t);
-
-	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
-		tunnel_dst_reset(t);
-		return NULL;
-	}
-
-	return dst;
-}
-
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev,
-						struct rtnl_link_stats64 *tot)
-{
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_sw_netstats *tstats =
-						   per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_bh(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
+	if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+		dst = NULL;
+	if (dst) {
+		if (dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+			tunnel_dst_reset(t);
+			dst_release(dst);
+			dst = NULL;
+		}
 	}
-
-	tot->multicast = dev->stats.multicast;
-
-	tot->rx_crc_errors = dev->stats.rx_crc_errors;
-	tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
-	tot->rx_length_errors = dev->stats.rx_length_errors;
-	tot->rx_frame_errors = dev->stats.rx_frame_errors;
-	tot->rx_errors = dev->stats.rx_errors;
-
-	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
-	tot->tx_dropped = dev->stats.tx_dropped;
-	tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
-	tot->tx_errors = dev->stats.tx_errors;
-
-	tot->collisions  = dev->stats.collisions;
-
-	return tot;
+	rcu_read_unlock();
+	return (struct rtable *)dst;
 }
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
 
 static bool ip_tunnel_key_match(const struct ip_tunnel_parm *p,
 				__be16 flags, __be32 key)
@@ -224,6 +169,7 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (remote != t->parms.iph.daddr ||
+		    t->parms.iph.saddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -240,10 +186,11 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 	head = &itn->tunnels[hash];
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
-		if ((local != t->parms.iph.saddr &&
-		     (local != t->parms.iph.daddr ||
-		      !ipv4_is_multicast(local))) ||
-		    !(t->dev->flags & IFF_UP))
+		if ((local != t->parms.iph.saddr || t->parms.iph.daddr != 0) &&
+		    (local != t->parms.iph.daddr || !ipv4_is_multicast(local)))
+			continue;
+
+		if (!(t->dev->flags & IFF_UP))
 			continue;
 
 		if (!ip_tunnel_key_match(&t->parms, flags, key))
@@ -260,6 +207,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn,
 
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (t->parms.i_key != key ||
+		    t->parms.iph.saddr != 0 ||
+		    t->parms.iph.daddr != 0 ||
 		    !(t->dev->flags & IFF_UP))
 			continue;
 
@@ -286,13 +235,17 @@ static struct hlist_head *ip_bucket(struct ip_tunnel_net *itn,
 {
 	unsigned int h;
 	__be32 remote;
+	__be32 i_key = parms->i_key;
 
 	if (parms->iph.daddr && !ipv4_is_multicast(parms->iph.daddr))
 		remote = parms->iph.daddr;
 	else
 		remote = 0;
 
-	h = ip_tunnel_hash(parms->i_key, remote);
+	if (!(parms->i_flags & TUNNEL_KEY) && (parms->i_flags & VTI_ISVTI))
+		i_key = 0;
+
+	h = ip_tunnel_hash(i_key, remote);
 	return &itn->tunnels[h];
 }
 
@@ -315,6 +268,7 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	__be32 remote = parms->iph.daddr;
 	__be32 local = parms->iph.saddr;
 	__be32 key = parms->i_key;
+	__be16 flags = parms->i_flags;
 	int link = parms->link;
 	struct ip_tunnel *t = NULL;
 	struct hlist_head *head = ip_bucket(itn, parms);
@@ -322,9 +276,9 @@ static struct ip_tunnel *ip_tunnel_find(struct ip_tunnel_net *itn,
 	hlist_for_each_entry_rcu(t, head, hash_node) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
-		    key == t->parms.i_key &&
 		    link == t->parms.link &&
-		    type == t->dev->type)
+		    type == t->dev->type &&
+		    ip_tunnel_key_match(&t->parms, flags, key))
 			break;
 	}
 	return t;
@@ -442,14 +396,13 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 					  struct ip_tunnel_net *itn,
 					  struct ip_tunnel_parm *parms)
 {
-	struct ip_tunnel *nt, *fbt;
+	struct ip_tunnel *nt;
 	struct net_device *dev;
 
 	BUG_ON(!itn->fb_tunnel_dev);
-	fbt = netdev_priv(itn->fb_tunnel_dev);
 	dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
 	if (IS_ERR(dev))
-		return NULL;
+		return ERR_CAST(dev);
 
 	dev->mtu = ip_tunnel_bind_dev(dev);
 
@@ -467,9 +420,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(iph->daddr)) {
-		/* Looped back packet, drop it! */
-		if (rt_is_output_route(skb_rtable(skb)))
-			goto drop;
 		tunnel->dev->stats.multicast++;
 		skb->pkt_type = PACKET_BROADCAST;
 	}
@@ -492,6 +442,8 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		tunnel->i_seqno = ntohl(tpi->seq) + 1;
 	}
 
+	skb_reset_network_header(skb);
+
 	err = IP_ECN_decapsulate(iph, skb);
 	if (unlikely(err)) {
 		if (log_ecn_error)
@@ -584,13 +536,14 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	struct flowi4 fl4;
 	u8     tos, ttl;
 	__be16 df;
-	struct rtable *rt = NULL;	/* Route to the other host */
+	struct rtable *rt;		/* Route to the other host */
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
-	bool connected = true;
+	bool connected;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	connected = (tunnel->parms.iph.daddr != 0);
 
 	dst = tnl_params->daddr;
 	if (dst == 0) {
@@ -657,8 +610,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
 			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
 
-	if (connected)
-		rt = (struct rtable *)tunnel_dst_check(tunnel, 0);
+	rt = connected ? tunnel_rtable_get(tunnel, 0) : NULL;
 
 	if (!rt) {
 		rt = ip_route_output_key(tunnel->net, &fl4);
@@ -716,12 +668,13 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		dev->needed_headroom = max_headroom;
 
 	if (skb_cow_head(skb, dev->needed_headroom)) {
+		ip_rt_put(rt);
 		dev->stats.tx_dropped++;
 		kfree_skb(skb);
 		return;
 	}
 
-	err = iptunnel_xmit(rt, skb, fl4.saddr, fl4.daddr, protocol,
+	err = iptunnel_xmit(skb->sk, rt, skb, fl4.saddr, fl4.daddr, protocol,
 			    tos, ttl, df, !net_eq(tunnel->net, dev_net(dev)));
 	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
 
@@ -766,26 +719,25 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 		if (set_mtu)
 			dev->mtu = mtu;
 	}
-	tunnel_dst_reset_all(t);
+	ip_tunnel_dst_reset_all(t);
 	netdev_state_change(dev);
 }
 
 int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 {
 	int err = 0;
-	struct ip_tunnel *t;
-	struct net *net = dev_net(dev);
-	struct ip_tunnel *tunnel = netdev_priv(dev);
-	struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
+	struct ip_tunnel *t = netdev_priv(dev);
+	struct net *net = t->net;
+	struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id);
 
 	BUG_ON(!itn->fb_tunnel_dev);
 	switch (cmd) {
 	case SIOCGETTUNNEL:
-		t = NULL;
-		if (dev == itn->fb_tunnel_dev)
+		if (dev == itn->fb_tunnel_dev) {
 			t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
-		if (t == NULL)
-			t = netdev_priv(dev);
+			if (t == NULL)
+				t = netdev_priv(dev);
+		}
 		memcpy(p, &t->parms, sizeof(*p));
 		break;
 
@@ -796,16 +748,20 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 			goto done;
 		if (p->iph.ttl)
 			p->iph.frag_off |= htons(IP_DF);
-		if (!(p->i_flags&TUNNEL_KEY))
-			p->i_key = 0;
-		if (!(p->o_flags&TUNNEL_KEY))
-			p->o_key = 0;
+		if (!(p->i_flags & VTI_ISVTI)) {
+			if (!(p->i_flags & TUNNEL_KEY))
+				p->i_key = 0;
+			if (!(p->o_flags & TUNNEL_KEY))
+				p->o_key = 0;
+		}
 
 		t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type);
 
-		if (!t && (cmd == SIOCADDTUNNEL))
+		if (!t && (cmd == SIOCADDTUNNEL)) {
 			t = ip_tunnel_create(net, itn, p);
-
+			err = PTR_ERR_OR_ZERO(t);
+			break;
+		}
 		if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
 			if (t != NULL) {
 				if (t->dev != dev) {
@@ -832,8 +788,9 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 		if (t) {
 			err = 0;
 			ip_tunnel_update(itn, t, dev, p, true);
-		} else
-			err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
+		} else {
+			err = -ENOENT;
+		}
 		break;
 
 	case SIOCDELTUNNEL:
@@ -927,6 +884,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 	}
 	rtnl_unlock();
@@ -1048,19 +1006,13 @@ int ip_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	struct iphdr *iph = &tunnel->parms.iph;
-	int i, err;
+	int err;
 
 	dev->destructor	= ip_tunnel_dev_free;
-	dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!dev->tstats)
 		return -ENOMEM;
 
-	for_each_possible_cpu(i) {
-		struct pcpu_sw_netstats *ipt_stats;
-		ipt_stats = per_cpu_ptr(dev->tstats, i);
-		u64_stats_init(&ipt_stats->syncp);
-	}
-
 	tunnel->dst_cache = alloc_percpu(struct ip_tunnel_dst);
 	if (!tunnel->dst_cache) {
 		free_percpu(dev->tstats);
@@ -1095,7 +1047,7 @@ void ip_tunnel_uninit(struct net_device *dev)
 	if (itn->fb_tunnel_dev != dev)
 		ip_tunnel_del(netdev_priv(dev));
 
-	tunnel_dst_reset_all(tunnel);
+	ip_tunnel_dst_reset_all(tunnel);
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_uninit);